© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 4245
    Prev
    Next
    INDEX
    Explanations

    words related to specific terms like "zebra," "unicorn," and "Buenos Aires."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific species and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     helic
    -0.74
     coh
    -0.69
     newsp
    -0.69
    fml
    -0.68
    desktop
    -0.67
    ories
    -0.66
     rub
    -0.66
     FML
    -0.65
    oire
    -0.64
     hemor
    -0.63
    POSITIVE LOGITS
    ruary
    0.77
    odied
    0.75
    allel
    0.75
    utsche
    0.74
    odus
    0.73
    atro
    0.71
    etheus
    0.71
    berus
    0.70
     Aires
    0.69
    iped
    0.69
    Activations Density 0.028%

    No Known Activations